Tootfinder

Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
Marouane Il Idrissi, Agathe Fernandes Machado, Arthur Charpentier
https://arxiv.org/abs/2506.13900

Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
Cooperative game theory has become a cornerstone of post-hoc interpretability in machine learning, largely through the use of Shapley values. Yet, despite their widespread adoption, Shapley-based methods often rest on axiomatic justifications whose relevance to feature attribution remains debatable. In this paper, we revisit cooperative game theory from an interpretability perspective and argue for a broader and more principled use of its tools. We highlight two general families of efficient al…

New allocation rule based on graph structures and their application to economic phenomena
Taiki Yamada, Taisuke Matsubae, Tomoya Akamatsu
https://arxiv.org/abs/2507.11808

New allocation rule based on graph structures and their application to economic phenomena
This study introduces the \emph{edge-based Shapley value}, a novel allocation rule within cooperative game theory, specifically tailored for networked systems, where value is generated through interactions represented by edges. Traditional allocation rules, such as the Shapley and Myerson values, evaluate player contributions based on node-level characteristics, or connected components. However, these approaches often fail to adequately capture the functional role of edges, which are crucial in…

Infrastructuring Contestability: A Framework for Community-Defined AI Value Pluralism
Andreas Mayer
https://arxiv.org/abs/2507.05187 https://

Infrastructuring Contestability: A Framework for Community-Defined AI Value Pluralism
The proliferation of AI-driven systems presents a fundamental challenge to Human-Computer Interaction (HCI) and Computer-Supported Cooperative Work (CSCW), often diminishing user agency and failing to account for value pluralism. Current approaches to value alignment, which rely on centralized, top-down definitions, lack the mechanisms for meaningful contestability. This leaves users and communities unable to challenge or shape the values embedded in the systems that govern their digital lives,…

Fermionic operatorial model of a system with competitive and cooperative interactions
M. Gorgone, G. Inferrera, F. Oliveri
https://arxiv.org/abs/2505.21554

Fermionic operatorial model of a system with competitive and cooperative interactions
An operatorial model of a system made by $N$ agents interacting each other with mechanisms that can be thought of as cooperative or competitive is presented. We associate to each agent an annihilation, creation and number fermionic operator, and interpret the mean values of the number operators over an initial condition as measures of the agents' wealth status. The dynamics of the system is assumed to be ruled by a Hermitian Hamiltonian operator $\mathcal{H}$, and the classical Heisenberg view …

An operatorial view of competition and cooperation in a network of economic agents
G. Giunta, M. Gorgone, F. Oliveri
https://arxiv.org/abs/2505.22917 https…

An operatorial view of competition and cooperation in a network of economic agents
A network of agents interacting both with competitive and/or cooperative mechanisms is modeled by using fermionic ladder operators. The time evolution of the network is assumed to be governed by a Hermitian time-independent Hamiltonian operator, and the mean values of the number operators are interpreted as a measure of the wealth status of the agents. Besides classical Heisenberg, we use the recently introduced $(H,ρ)$-induced dynamics approach to account for some actions able to provide a se…